Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint, openWorldHint), and the description adds real operational context beyond them: the window is today−N through today inclusive with today being incomplete, results are sorted by cost descending, and campaign_urn is replaced by the campaign name for the 20 highest-cost campaigns only. That last detail is a non-obvious output transformation an agent would otherwise misread. No auth or rate-limit notes, so not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded with the purpose and then devotes each line to one concern (time window, return fields, sorting, metric definitions, workspace), with no filler. It is dense rather than padded, though the metric-definition block could be tightened slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, yet the description still usefully clarifies the ambiguous return fields (conversions vs leads vs lead_form_opens, cost in account currency, urn-vs-name substitution). Combined with the time-window and sorting semantics, an agent has enough to call and interpret it correctly; only sibling routing is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the parameters and it largely does: 'days' is defined as today−N through today inclusive with today incomplete, and 'workspace' is defined as the client workspace slug that is optional when only one workspace exists. Only minor gaps remain, e.g. no stated bounds or default behavior for days beyond the schema default of 30.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource and verb scope: LinkedIn Ads campaign performance with an explicit metric list (impressions, clicks, cost, conversions, leads) over the last N days. It is clearly campaign-level, but it never distinguishes itself from the close sibling linkedin_performance_report or from linkedin_creative_performance / linkedin_audience_breakdown, so an agent must infer the split.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is one genuinely useful usage rule: for lead-gen campaigns evaluate 'leads', not 'conversions'. It also notes workspace is optional when only one workspace exists. However, there is no guidance on when to pick this over linkedin_performance_report or the creative/audience breakdown tools, so the choice between siblings is left implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.